dragon-qwen-7b-ov

dragon-qwen-7b-ov is an OpenVino int4 quantized version of dragon-qwen-7b, providing a very fast inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

dragon-qwen-7b is a fact-based question-answering model, optimized for complex business documents.

This is a very accurate model and a new release based on Qwen2.

Model Description

• Developed by: llmware
• Model type: qwen2-7b
• Parameters: 7 billion
• Model Parent: llmware/dragon-qwen-7b
• Language(s) (NLP): English
• License: Apache 2.0
• Uses: Fact-based question-answering
• RAG Benchmark Accuracy Score: 99.0
• Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website